FIFA’s four major data sources

13:42Okay. >> Um which I think again is it's really cool in its own reason right because all the only information that we know from that data is who has the ball at every frame. Outside of that we just have the player location uh 50 times a second. Um but when it comes to the other kind of data ecosystem or the full data e ecosystem that we have um we have a joint venture with Hawkeye for example. So when it comes to TV what you will see is all of our data and our data model that we've built over the last couple of years um which is a lot different to most other providers for example but then that's automated. So that is

14:22automated through a number of um computer vision processes and algorithms to identify a lot of machine learning has gone into that to identify what uh the events actually look like and then to automatically categorize them. Um so Juan I don't know whether you want to give a little bit more detail on that process. >> Yeah so as I mentioned we have I would say four different sources of data. One is the tracking data from the players that as he mentioned comes every 20 milliseconds and provides a lot of context and information uh just by

15:02looking at how the dynamic of the players is on the page. Then we have the event data that it's also we have a version live and then we have a version postmatch that it's uh basically scrapped and cleaner and following what we have developed which is the FIFA football language which is what Aaron hinted before and this data is extremely precise to the frame what the players make contact with the ball or perform a particular action and very detailed also of how These events are basically not only if it was a left or right foot, but what kind of pass, who was a receiver, how and etc. So each of

15:44the events has its own set of traits and characteristics. We also have a lot of limb tracking data that it's also used for other components in football like the AR for example. And then we also have the ball data which is very very high resolution. uh it's 500 me um frames per second and we get a lot of information from it. It's a very complex data set because it has a lot of um let's say components but uh but yeah it's very enriching as well not only the ball position but also like the rotational accelerometers etc. So, so

16:26it's so those are the the main data sets, but as Aaron mentioned for momentum, we focus mostly on the I mean only on the tracking data because that's where we get all that context of the players. What are they doing? How are they running, interacting, and so >> that's that's very I mean there there's so many interesting pieces here because I think we're sort of there's sort of two separate conversations here, right? which is the entire pipeline of data that informs a variety of different end products real time and postmatch uh is quite vast. Um but within that context the the match momentum feature is actually a very small just a very narrow

17:08set of of the available context there. um which I it's so interesting and and